Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/shangyankeji/super-dev/claude-mdgit clone --depth 1 https://github.com/shangyankeji/super-devWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/shangyankeji/super-dev/claude-md)<a href="https://agentmods.dev/instructions/shangyankeji/super-dev/claude-md"><img src="https://agentmods.dev/badge/instructions/shangyankeji/super-dev/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03366 | $0.03366 |
| Opus 5 | $0.01683 | $0.01683 |
| Sonnet 5 | $0.00673 | $0.00673 |
| Haiku 4.5 | $0.00337 | $0.00337 |
Grade A, and why
super-dev CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Super Dev is a Python CLI tool (v2.4.0) that orchestrates AI-driven development pipelines inside host environments (e.g., Claude Code). It provides governance, quality gates, and audit artifacts for commercial-grade software delivery. It is NOT an independent AI agent — it's a governance layer that runs inside a host's coding environment.
Build & Development Commands
# Install in development mode (requires Python 3.10+)
pip install -e ".[dev]"
# Run the CLI
super-dev
# Linting & formatting
ruff check super_dev/ # lint
ruff check --fix super_dev/ # auto-fix lint issues
black super_dev/ --check # check formatting
black super_dev/ # apply formatting
# Type checking
mypy super_dev/
# Run all tests
pytest
# Run a single test file
pytest tests/unit/test_workflow.py
# Run a specific test
pytest tests/unit/test_workflow.py::test_function_name -v
# Run with coverage
pytest --cov=super_dev
Code Style
- Line length: 100 (configured in both ruff and black)
- Target Python: 3.10+
- Ruff rules: E, F, I, N, W, UP (E501 ignored)
- All imports must be sorted (ruff
Irule)
Architecture
Core Pipeline (super_dev/)
The CLI entry point is super_dev/cli.py (~6k lines), built as a large class composed via mixins:
cli_parser_mixin.py— argparse command definitionscli_analysis_mixin.py— analysis subcommandscli_governance_mixin.py— governance/enforcement subcommandscli_host_ops_mixin.py— host tool operationscli_experience_mixin.py— UX enhancementscli_deploy_runtime_mixin.py— deployment/runtime commandscli_release_quality_mixin.py— release & quality commandscli_spec_mixin.py— spec management commands
Pipeline Orchestration (super_dev/orchestrator/)
engine.py— main pipeline engine driving phase transitionsgovernance.py— governance policy enforcement during pipelineknowledge.py/knowledge_pusher.py— knowledge injection into pipeline stagesquality.py— quality gate evaluationcontracts.py— pipeline contract definitions
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 272 lines · 3,366 tokens per session scan A 9cae499efca6
super-dev CLAUDE.md is an instructions file published in the GitHub repository shangyankeji/super-dev (274 stars, last pushed 2mo ago), licensed MIT. It adds 3,366 tokens to every session, about $0.0168 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
truthmark AGENTS.md
AGENTS.md instructions for merlinhu1/truthmark, covering authority, documentation scope, product boundary, rules and instruction surface boundary.
coco-workflow CLAUDE.md
Instructions for skullninja/coco-workflow, covering claude.md -- coco, project overview, architecture, key files and tracker (lib/tracker.sh).
agent-feed AGENTS.md
Instructions for fqmyysjjd/agent-feed, covering agent-feed ai development instructions, startup policy, rule priority, responsibility boundary and mandatory gates.
agent-feed CLAUDE.md
Instructions for fqmyysjjd/agent-feed, a project described as: Turn AI coding chats into a source-controlled workflow: AGENTS.md, rules, skills, verification gates, and adapters for Codex, Claude Code, and Cursor.
truthmark CLAUDE.md
Claude Code instructions for merlinhu1/truthmark, covering authority, documentation scope, product boundary, rules and instruction surface boundary.
loop-lang CLAUDE.md
Claude Code instructions for tickets-forge-dev/loop-lang: This repo uses Loop — a small natural-language DSL for self-correcting, human-gated coding workflows. First time you touch Loop in this repo, read AGENTS.md end to end before authoring or running anything — it's the full, current grammar that ships with the…